control
Control bkit automation level (L0-L4), view trust score, and manage guardrails. Trust level directly drives SPRINT_AUTORUN_SCOPE (v2.1.13): L0…
Skills
Find an Agent Skill for your task. Read the guide and copy the install command.
Updated 11-02 00:09
Agents & models
25,470 results
grill-me
Deep user interview for pivotal plan/design uncertainties. Auto-suggest when user judgment would materially change scope, approach, or success criteria. Scoped…
audio-language-models
Gemini Live API, Grok Voice Agent, GPT-4o-Transcribe, AssemblyAI patterns for real-time voice, speech-to-text, and TTS. Use when implementing voice agents,…
langfuse-observability
LLM observability platform for tracing, evaluation, prompt management, and cost tracking. Use when setting up Langfuse, monitoring LLM costs, tracking token…
langgraph-human-in-loop
LangGraph human-in-the-loop patterns. Use when implementing approval workflows, manual review gates, user feedback integration, or interactive agent…
mcp-advanced-patterns
Advanced MCP patterns for tool composition, resource management, and scaling. Build custom MCP servers, compose tools, manage resources efficiently. Use when…
multi-agent-orchestration
Multi-agent coordination and synthesis patterns. Use when orchestrating multiple specialized agents, implementing fan-out/fan-in workflows, or synthesizing…
vision-language-models
GPT-5/4o, Claude 4.5, Gemini 2.5/3, Grok 4 vision patterns for image analysis, document understanding, and visual QA. Use when implementing image captioning,…
ai-pro
Professional AI and System Orchestrator. Specialized in GPT-5, autonomous agents, Auth.js v5, Stripe v13, Monorepos (Bun/pnpm), and large codebase…
context-distiller
Senior Context Architect & Memory Engineer. Expert in Automated Context Packing, Symbol Indexing, and Agent Rehydration for 2026.
zeno-brainstorming
Use when you have a rough idea and want to refine it into a well-formed proposal before submitting to Nexus. Must check directive first - all ideas must align…
zoe-creating-tasks
Use when a Nexus project is ready and needs work breakdown into self-contained, time-boxed tasks for contributors. Combines planning research with immediate…
zoe-heartbeat
Execute this skill on every heartbeat tick. Recommended frequency: every 30 minutes. Zoe maintainer routine: monitor Nexus state, coordinate agents, check…
fleet-worker
One cheap headless Claude Code worker on a cheaper brain (GLM via z.ai, or Sonnet/Haiku) - full tool harness, isolated git worktree + CLAUDE_CONFIG_DIR -…
agent-swarm-orchestrator
Designs multi-agent systems with coordinated agent swarms, task distribution, inter-agent communication, and emergent collective behavior.
blockchain-integration-builder
Design and implement blockchain integrations across chains and frameworks with emphasis on patterns over specific technologies. Use when building Web3…
local-llm-fine-tuning
Guides users through the process of preparing datasets and fine-tuning local Large Language Models (LLMs) using techniques like LoRA and QLoRA.
mcp-builder
Guide for creating high-quality MCP (Model Context Protocol) servers that enable LLMs to interact with external services through well-designed tools. Use when…
agent
Dispatch tasks to the opencode agent for execution, automatically recording the processing to separate log files
find-skills
Use when user asks to find, install, or search for agent skills. Also use when user asks 'can you do X' or 'is there a skill for X' where X is a specialized…
task-planning
Adapt one explicitly targeted or unambiguously current agreed Feature into a user-confirmed graph of independent, agent-ready child Tasks. Use when a Feature…
skill-finder
Find the right Affitor skill for your goal. Triggers on: "which skill should I use", "find me a skill", "what skills are available", "help me choose a skill",…
chat_with_agent
Use this skill when you need to consult another agent, ask for help, or involve a specific agent the user asked for.
make_plan
For external plan request scenarios, guides the Agent to request a clear, actionable, step-by-step plan from a stronger Agent via list_agents and…